haowei
commited on
Commit
•
1e8a310
1
Parent(s):
9cb7040
add model
Browse files- config.json +7 -2
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,5 +1,7 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
|
|
|
|
3 |
"adapters": {
|
4 |
"adapters": {},
|
5 |
"config_map": {},
|
@@ -7,12 +9,14 @@
|
|
7 |
"fusions": {}
|
8 |
},
|
9 |
"architectures": [
|
10 |
-
"
|
11 |
],
|
12 |
"attention_probs_dropout_prob": 0.1,
|
|
|
13 |
"bos_token_id": 0,
|
14 |
"classifier_dropout": null,
|
15 |
"eos_token_id": 2,
|
|
|
16 |
"hidden_act": "gelu",
|
17 |
"hidden_dropout_prob": 0.1,
|
18 |
"hidden_size": 768,
|
@@ -25,6 +29,7 @@
|
|
25 |
"num_hidden_layers": 12,
|
26 |
"pad_token_id": 1,
|
27 |
"position_embedding_type": "absolute",
|
|
|
28 |
"torch_dtype": "float32",
|
29 |
"transformers_version": "4.11.3",
|
30 |
"type_vocab_size": 1,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/home/haowei/haowei/continual-post-training/agnews_unsup_roberta",
|
3 |
+
"adapter_mode": "parallel",
|
4 |
+
"adapter_task": 5,
|
5 |
"adapters": {
|
6 |
"adapters": {},
|
7 |
"config_map": {},
|
|
|
9 |
"fusions": {}
|
10 |
},
|
11 |
"architectures": [
|
12 |
+
"RobertaMaskForSequenceClassification"
|
13 |
],
|
14 |
"attention_probs_dropout_prob": 0.1,
|
15 |
+
"attn_adapter_size": 512,
|
16 |
"bos_token_id": 0,
|
17 |
"classifier_dropout": null,
|
18 |
"eos_token_id": 2,
|
19 |
+
"ffn_adapter_size": 768,
|
20 |
"hidden_act": "gelu",
|
21 |
"hidden_dropout_prob": 0.1,
|
22 |
"hidden_size": 768,
|
|
|
29 |
"num_hidden_layers": 12,
|
30 |
"pad_token_id": 1,
|
31 |
"position_embedding_type": "absolute",
|
32 |
+
"smax": 400,
|
33 |
"torch_dtype": "float32",
|
34 |
"transformers_version": "4.11.3",
|
35 |
"type_vocab_size": 1,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e17d312f7eeafb919e61b2e50fa0216dfe446599d1991c22e983aee7e9147c9c
|
3 |
+
size 593931417
|